INDEX

Explanations

phrases or words specifically consisting of " &"

oai_token-act-pair · gpt-3.5-turbo

conjunctions and symbols indicating connections or relationships

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atche

-0.88

etheless

-0.76

ionage

-0.74

isoft

-0.73

senal

-0.71

sembly

-0.70

blance

-0.70

 misunder

-0.68

iguous

-0.67

ossier

-0.65

POSITIVE LOGITS

 Friends

0.83

GAN

0.83

^^^^

0.79

#$

0.76

++++++++++++++++

0.76

Co

0.73

optional

0.69

 Associates

0.68

nect

0.68

vine

0.67

Activations Density 0.036%

phrases or words specifically consisting of " &"

conjunctions and symbols indicating connections or relationships

No Comments

No Known Activations